© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17338
    Prev
    Next
    INDEX
    Explanations

    bri, fri, uri prefixes to words

    np_acts-logits-general · gemini-2.5-flash-lite

    ri, stri, cri, gri, bri starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    र्वाद
    0.42
    뤘
    0.40
    鰱
    0.40
     Gewalt
    0.39
    Starting
    0.39
     thơ
    0.39
     dó
    0.38
    roidism
    0.38
     हराया
    0.36
    톨
    0.36
    POSITIVE LOGITS
    ault
    0.52
    anna
    0.46
    ks
    0.46
    umphed
    0.44
    ki
    0.43
    ku
    0.43
    bery
    0.43
    kin
    0.42
     ripples
    0.42
    knings
    0.42
    Activations Density 0.050%

    No Known Activations